Vision and Attention Theory Based Sampling for Continuous Facial Emotion Recognition

Abstract

Affective computing-the emergent field in which com-1 puters detect emotions and project appropriate expressions of their 2 own-has reached a bottleneck where algorithms are not able to 3 infer a person's emotions from natural and spontaneous facial ex-4 pressions captured in video. While the field of emotion recognition 5 has seen many advances in the past decade, a facial emotion 6 recognition approach has not yet been revealed which performs well 7 in unconstrained settings. In this paper, we propose a principled 8 method which addresses the temporal dynamics of facial emotions 9 and expressions in video with a sampling approach inspired from 10 human perceptual psychology. We test the efficacy of the method on 11 the Audio/Visual Emotion Challenge 2011 and 2012, Cohn-Kanade 12 and the MMI Facial Expression Database. The method shows an av-13 erage improvement of 9.8% over the baseline for weighted accuracy 14 on the Audio/Visual Emotion Challenge 2011 video-based frame-15 level subchallenge testing set.

A Hybrid Approach of Facial Emotion Detection using Genetic Algorithm along with Artificial Neural Network

“…In this paper, ANN is used as a classifier to train the proposed facial emotion recognition system based on optimized feature and on the basis of training of system, the classification of a test image from training structure of ANN can be done [4].…”

Background suppressing Gabor energy filtering

“…For class probability rates please refer to Ref. [9]. The true positive rate, false positive rate, false negative rate, true negative rate, precision, recall and F 1 -score are given in Table 3.…”

Facial emotion recognition using min-max similarity classifier

“…Facial emotion recognition is the identification of a human emotion based on the facial expression and mimics [6]. The facial emotion recognition has a wide range of appliction prospects in different areas, such as medicine [7], robotics [8], [9], computer vision, surveillance systems [1], machine learning [10], artificial intelligence, communication [11], [12], psychological studies [4], smart vehicles [9], security and embedded systems [13].…”

“…Facial emotion recognition accuracy depends on the robustness of a feature extraction method to intra-class variations and classifier performance under noisy conditions and with various types of occlusions [10]. Even thought a variety of approaches for the automated recognition of human expressions from the face images using template matching methods have been investigated and proposed over the last few years [14], the emotion recognition method with robust feature extraction and effective classification techniques accompanied by low computational complexity is still an open research problem [21].…”